# LungVis 1.0: light-sheet fluorescence microscopy (LSFM) of 78 cleared mouse lungs with AI airway segmentations and nanoparticle deposition

## Facts

- Provider: L. Yang, Q. Liu, P. Kumar et al. (Helmholtz Munich); mirrored by MedOtter
- License: CC-BY-4.0 (https://zenodo.org/records/7413818)
- Size: 606 files
- Format: PNG, TIFF (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/MedOtter/LungVis10
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.7413818
- Category: Life Sciences
- Source: https://doi.org/10.1038/s41467-024-54267-1
- Page: https://scigantic.com/archive/8d18b565-b76b-5a84-952b-a48342a69474
- Keywords: Life Sciences, image segmentation, PNG, TIFF, Hugging Face

## About

LungVis 1.0 is a whole-organ 3D imaging dataset of tissue-cleared mouse lungs (C57BL/6) imaged by light-sheet fluorescence microscopy (LSFM), from Helmholtz Munich. Each of the 78 lungs has an autofluorescence channel showing lung structure, a fluorescence channel showing where inhaled or instilled nanoparticles landed, and nnU-Net generated airway segmentations, for studying airway geometry and how drugs or particles are deposited inside the lung acini. The groups cover healthy lung structure scans (Lung_001 to Lung_041) and four routes of pulmonary delivery: intranasal liquid aspiration (INLA), intratracheal liquid instillation (ITLI), ventilator-assisted aerosol delivery (VAAD) and nose-only aerosol inhalation (NOAI). Each lung folder holds 01_Raw imaging data_compressed, 02_AI results and 03_Processed data subfolders with multi-gigabyte TIFF stacks and PNG renderings; about 480 GB in total (measured 2026-11-21); read TIFF stacks with tifffile. Mirrored by MedOtter from the authors' Zenodo record (DOI 10.5281/zenodo.7413818), released under CC BY 4.0. Cite Yang et al., Nature Communications 15:10138 (2024), doi 10.1038/s41467-024-54267-1.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="MedOtter/LungVis10", filename="INLA_001/INLA_001/01_Raw imaging data/INLA_001_Raw_AF520+NP640nm_UID_18-35-57_3D.png", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: PNG, TIFF

Example file: `INLA_001/INLA_001/01_Raw imaging data/INLA_001_Raw_AF520+NP640nm_UID_18-35-57_3D.png`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/8d18b565-b76b-5a84-952b-a48342a69474
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/8d18b565-b76b-5a84-952b-a48342a69474
- Over MCP: `get_schema_card` with id `8d18b565-b76b-5a84-952b-a48342a69474` at https://api.scigantic.com/mcp

## Related topics

- [TIFF datasets](https://scigantic.com/topics/tiff)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [PNG datasets](https://scigantic.com/topics/png)
- [Life Sciences datasets](https://scigantic.com/topics/life-sciences)
